Flexible non-parametric regression models for compositional data

DOI10.48550/ARXIV.2002.05137MaRDI QIDQ69799zbMATH OpenOpenAlexFDO

Authors Abdulaziz Alenazi, Connie Stewart, Michail Tsagris, Michail Tsagris, Abdulaziz Alenazi, Connie Stewart

Publication date 12 February 2020

Published in Statistics and Computing (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2002.05137

zbMATH Keywords

\(\alpha\)-transformation\(k\)-NN algorithmcompositional datakernel regressionregression

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Nonparametric regression and quantile regression (62G08) Multivariate analysis (62H99)

Abstract: Compositional data arise in many real-life applications and versatile methods for properly analyzing this type of data in the regression context are needed. When parametric assumptions do not hold or are difficult to verify, non-parametric regression models can provide a convenient alternative method for prediction. To this end, we consider an extension to the classical $k$--$NN$ regression, termed $alpha$--$k$--$NN$ regression, that yields a highly flexible non-parametric regression model for compositional data through the use of the $alpha$-transformation. Our model is further extended to the $alpha$--kernel regression by adopting the Nadaraya-Watson estimator. Unlike many of the recommended regression models for compositional data, zeros values (which commonly occur in practice) are not problematic and they can be incorporated into the proposed models without modification. Extensive simulation studies and real-life data analyses highlight the advantage of using these non-parametric regressions for complex relationships between the compositional response data and Euclidean predictor variables. Both suggest that $alpha$--$k$--$NN$ and $alpha$--kernel regressions can lead to more accurate predictions compared to current regression models which assume a, sometimes restrictive, parametric relationship with the predictor variables. In addition, the $alpha$--$k$--$NN$ regression, in contrast to current regression techniques, enjoys a high computational efficiency rendering it highly attractive for use with large scale, massive, or big data.

Recommendations

• Regression analysis with compositional data containing zero values
• A Dirichlet regression model for compositional data with zeros
• Regression for Compositional Data by using Distributions Defined on the Hypersphere
• A transformation‐free linear regression for compositional outcomes and predictors
• Spatial regression modeling for compositional data with many zeros

Cites work

• scientific article; zbMATH DE number 1194132 (Why is no real title available?)
• scientific article; zbMATH DE number 3772748 (Why is no real title available?)
• scientific article; zbMATH DE number 847282 (Why is no real title available?)
• scientific article; zbMATH DE number 3221828 (Why is no real title available?)
• scientific article; zbMATH DE number 3222478 (Why is no real title available?)
• A Dirichlet regression model for compositional data with zeros
• A Simplex Method for Function Minimization
• A folded model for compositional data analysis
• A logistic normal multinomial regression model for microbiome compositional data analysis
• A semiparametric model for compositional data analysis in presence of covariates on the simplex.
• A statistical assessment of Buchanan's vote in Palm Beach county
• Colours and cocktails: compositional data analysis 2013 Lancaster lecture
• Convergence of functional \(k\)-nearest neighbor regression estimate with functional responses
• Dealing with zeros and missing values in compositional data sets using nonparametric imputation
• Dirichlet component regression and its applications to psychiatric data
• Gaussian asymptotic limits for the \({\alpha}\)-transformation in the analysis of compositional data
• Geometric approach to statistical analysis on the simplex
• Grain-size control on petrographic composition of sediments: Compositional regression and rounded zeros
• Improved classification for compositional data using the \(\alpha\)-transformation
• Intrinsic statistics on Riemannian manifolds: Basic tools for geometric measurements
• Isometric logratio transformations for compositional data analysis
• Limit theorems for empirical Fréchet means of independent and non-identically distributed manifold-valued random variables
• Model-based replacement of rounded zeros in compositional data: classical and robust approaches
• Modeling compositional data using Dirichlet regression models
• Multinomial logistic regression algorithm
• Multivariate fractional regression estimation of econometric share models
• Non-parametric regression for compositional data
• Principal component analysis of compositional data
• Random Forests and Adaptive Nearest Neighbors
• Random forests
• Regression analysis for microbiome compositional data
• Regression analysis of multivariate fractional data
• Regression analysis with compositional data containing zero values
• Regression for Compositional Data by using Distributions Defined on the Hypersphere
• Robust Locally Weighted Regression and Smoothing Scatterplots
• Simplical regression the normal model
• Some restriction tests in a new class of regression models for proportions
• Spatial regression modeling for compositional data with many zeros
• Strong consistency of nearest neighbor regression function estimators
• The Helmert Matrices
• Using compositional and Dirichlet models for market share regression

Cited in

(2)

• Regression analysis with compositional data containing zero values
• Dealing with zeros and missing values in compositional data sets using nonparametric imputation

This page was built for publication: Flexible non-parametric regression models for compositional data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q69799)